Day 43 of #100daysofnetworks
Restart Sequence Completed; Back in Action
Alright, I have wanted to write a post for #100daysofnetworks for months and months and months, and no matter what, something was just always in the way. This year has been a challenging year, but I don’t want to dwell on that. Let’s get this going.
What have I been up to?
I have been quiet for way too long, and I have had a very active year. Even though I was not writing, I was busy being impacted by what I have learned during #100daysofnetworks. In particular, I previously wrote two very creative articles, showing how Natural Language Processing, Graph Theory, and Music can be fused together:
If you are a musician, you should definitely read those. Even if you are not a musician, pay attention to the notion that Natural Language Processing can be useful even beyond language.
These two articles literally ignited something in my musical learning. The outcome of these articles was that I had a clean graph of musical scale similarity, and I could use that to play with scales:
Which scales are similar enough with the minor scale that I can swap them in?
Which scales go with major chords?
Which scales go with minor chords?
When you are learning guitar, you do not always have a teacher accessible to you 24/7, so this was a cool experiment that ended up unlocking lead guitar for me, and then after that it led me back to folk roots, where I began to learn about Travis Picking and Clawhammer Technique. I got so into the learning that I made a YouTube Channel and added a lot of videos that helped me learn. I added 195 videos to that channel, showing how into the learning I got.
That explosive learning came from graph analysis. It did not start with picking up a guitar or flipping through my scale book. It came from building systems thinking around musical scales.
Really, that’s most of what I have been busy with this year, in terms of learning. It was a musical year for me, and I was unable to write, until now. So, I am excited to be back at it.
Please Support this Blog
I would like to make a special request in this article. This blog has over 600 subscribers. I have written over 40 articles. Each article typically involves about four hours of research and development, so that’s about 200 hours of valuable work and writing that I’ve provided for free, because most important is that I want people to learn this. I am not doing this to make money.
However, these days, there are things that I would like to do. For instance, to play with GraphRAG for AI, it is useful to have access to a Graph Database. The cheapest tier Neo4j instance is about $800/year. I would like to work on GraphRAG and write about it so that you all learn, but I cannot do that without support.
So, I have opened up a few ways for you to support this blog:
If you are a subscriber, please consider converting to a paid subscriber. I provide code, data files, and coding explanations that are absolutely worth more than $8 per month. But I understand that not everyone can afford to pay, and that’s fine. Free is absolutely fine, for those who need free.
If you are a paid or unpaid subscriber and you want more flexibility in your contributions, I set up a ko-fi account. CLICK HERE. You can use this this to buy me a coffee ($5 donation) or even to pitch in for a Neo4j Aura instance, which will enable more writing and learning.
AI Plus Graph
It’s known that graph is useful in AI stuff, but AI is also useful in graph stuff. :)
For instance, my latest research is into:
Can a prompt approach create better edgelists from text than previous approaches such as Named-Entity Recognition (NER) or Part-of-Speech Tagging?
Can AI agents be useful in providing a chat interface exploring and analyzing graphs?
The answer to both, I think, is yes. I have already begun the work. In fact, I already have a few of these AI-based edgelists and we will be analyzing them on an upcoming day, to validate how well the AI did in determining edges.
The agentic approach is also very cool and will be useful. Here is a preview. Notice that I am interacting with language.
What is Coming?
Part of the challenge in the last year was that AI was making moves that I couldn’t keep up with, and it was hard to write about it. Things seem more stable now, and we are in a time of usefulness. The previous image shown is an example. Being able to talk to a graph can make graph analysis much easier. AI can be useful for accessibility.
So, we’re going to make some pivots with this blog. I’ve already covered the basics a lot, and they’ll always be a part of any analysis, but moving forward, we are going to dive into:
Graph Machine Learning
Artificial Intelligence
Agentic Graph Analysis and Exploration
Prompt-based Graph Analysis and Exploration
Geospatial Analysis (Street Networks)
We’ve covered the basics well enough and it’s time to have a lot of fun. We will start with Graph Machine Learning. That will be the topic of the next post.
If you want to prepare for the next article, pick up a copy of this book and start reading. I am several chapters in and I love it. I also read the first edition of the book and loved it as well.
I don’t know exactly what changes they have made in the second edition, but it is great. If you enjoy this blog, you will probably enjoy this book.
My Book
I am also actively working on kicking off some book projects. I have a few in mind. Please let me know in the comments what sounds most useful to you.
Second Edition of Network Science with Python: My book was published in 2023, so I would like to modernize the code a bit and add a few chapters on temporal network analysis and artificial intelligence.
Network Science with Python Cookbook: This book would be a more tactical reference book than my original book. My original book gets you into the mindset of how I do what I do and how it can help you. But I would like to put together a tactical desktop reference book to supplement my book.
(Graphs: Zero to Hero): I am considering writing a book similar to my first but less about converting text into graphs and more about starting with graph data. Imagine you knew nothing about graph analysis and someone gave you an edgelist. “Oh shoot, what do I do now?” This book would cover that.
Source Code Analysis and Data Observability: I am considering writing a book on what originally led me to Network Science in the first place. This would be extremely useful to Data Operations Engineers and Site Reliability Engineers. It led our team at Intel to being able to troubleshoot mystery outages from days to minutes. This is a useful skill that I eventually need to write more about.
But please do buy a copy of my book if you haven’t already.
Need Any Help?
Finally… there’s no fun way to say this. I am out of a job and need to find work. If you work in Data Operations, Data Engineering, Cybersecurity, Data Science, or do anything with Artificial Intelligence or Machine Learning and you think I can be of use to your company, please reach out.
I need full-time work with benefits. I need a good problem to help solve. I enjoy collaborations, but I need to pay mortgage and expenses. I am very good at what I do, and I am very good at making companies more effective. I’m a very friendly person and a good teammate, so let me know if you think of anything. Or pitch in and buy a coffee to support this writing.
These Will Be More Frequent
100daysofnetworks was originally something I did daily, back in 2020. This is the second iteration. Life challenges have gradually slowed me down, to the point that this is the first new article since January. I don’t think I’ll get this back to daily, but these are going to be more frequent from now on. I will try to do at least one a week, and maybe more. Showing support would motivate me. I’m very excited to get back to this, back to learning, and back to being creative.
LET’S GOOOOOOOOO!
Chappie (ChatGPT) drew us a picture for this post. I let it proofread. I do not use it for writing. My words are my own.
Alright, with this. My day is complete. I am heading out. If you would like to buy me a coffee, here you go. And come say hi in the Substack comments!